Time Series

# data from: April 18, 2017
# lines for time series data
library(tidyverse)
df <- read_csv("mortgage.csv")
df <- df %>% gather(key = TYPE, value = RATE, -DATE)
ggplot(df, aes(DATE, RATE, fill = TYPE)) + geom_col() +
    ggtitle("U.S. Mortgage Rates", subtitle = "Not recommended!")

ggplot(df, aes(DATE, RATE, color = TYPE)) + geom_line() +
    ggtitle("U.S. Mortgage Rates")

df$TYPE <- factor(df$TYPE,
                  levels = c("30 YR FIXED", "15 YR FIXED",
                             "5/1 ARM"))

g <- ggplot(df, aes(DATE, RATE, color = TYPE)) + geom_line() +
    ggtitle("U.S. Mortgage Rates") +
    labs (x = "", y = "percent") +
    theme_grey(16) +
    theme(legend.title = element_blank())
g

library(lubridate)
df2010 <- df %>% filter(year(DATE) == 2010)
ggplot(df2010, aes(DATE, RATE, color = TYPE)) + geom_line() +
    ggtitle("U.S. Mortgage Rates")

set.seed(5702)
day <- 1:31
number <- 10 * (day - 14)^2 + 2000 + rnorm(1:31, 0, 400)
df <- data.frame(day, number)
ggplot(df, aes(day, number)) +
    geom_line(color = "deeppink") +
    geom_point(color = "deeppink") +
    scale_x_continuous(breaks = 1:31) +
    scale_y_continuous(limits = c(0, 5000)) +
    ggtitle("Average Motor Vehicle Inspections per Day",
            subtitle = "(fake data)") +
    labs(x = "day of month", y="number of inspections") +
    theme(plot.title = element_text(size = 16))

ggplot(df, aes(day, number)) +
    geom_col() +
    scale_x_continuous(breaks = 1:31) +
    ggtitle("Average Motor Vehicle Inspections per Day") +
    labs(x = "day of month", y="number of inspections") +
    theme(plot.title = element_text(size = 16))

dfman <- read_csv("ManchesterByTheSea.csv")
head(dfman)

g <- ggplot(dfman, aes(Date, Gross)) + 
  geom_line() +
    ggtitle("Manchester by the Sea",
            "Daily Gross, United States")
g

g + geom_line(color = "green") +
  geom_point(color = "green") + theme_halloween

library(lubridate)
g + geom_point(aes(color = factor(wday(Date, label = TRUE))))

g <- ggplot(dfman, aes(Date, Gross)) + geom_line() +
    ggtitle("Manchester by the Sea",
            "Daily Gross, United States")
saturday <- dfman %>% filter(wday(Date) == 7)
g + geom_point(data = saturday, aes(Date, Gross),
               color = "deeppink")

g + geom_text(data = saturday,
              aes(Date, Gross, label = "Sat"),
              color = "deeppink", size = 4)

g + geom_point(size = 1) + 
    geom_text(data = saturday,
              aes(Date, Gross + 50000, label = "Sat"),
              color = "deeppink", size = 4) +
    geom_point(data = saturday, aes(Date, Gross),
               color = "deeppink", size = 1.5)

library(plotly)
# this works
dfman <-read_csv("ManchesterByTheSea.csv")
p <- plot_ly(
    dfman, x = ~Date, y = ~Gross,
    type = 'scatter',
    mode = 'lines+markers',
    # Hover text:
    hoverinfo = 'text',
    text = ~paste(Day)
)
p

g + geom_point(data = saturday, aes(Date, Gross),
               color = "deeppink") +
    geom_smooth(color = "blue", se = FALSE)

g <- ggplot(dfman, aes(Date, Gross)) + geom_point()
g + geom_smooth(span = .15, se = FALSE)

g + geom_smooth(span = .4, se = FALSE)

g + geom_smooth(span = .6, se = FALSE)

g + geom_smooth(span = .8, se = FALSE)

g + geom_smooth(span = 1, se = FALSE)

g + geom_smooth(span = .05)

# lines grouped by color
ggplot(dfman, aes(Date, Gross)) +
    geom_smooth(color = "black") +
    geom_line(aes(color = wday(Date, label = TRUE)),
              lwd = 1) +
    geom_smooth(color = "black") +
    theme(legend.position = "bottom",
          legend.title = element_blank())

ggplot(dfman, aes(Date, Gross)) +
    geom_line(color = "grey30") + geom_point(size = 1) +
    facet_grid(.~wday(Date, label = TRUE))

ggplot(dfman, aes(Date, Gross)) +
    geom_line(color = "grey30") + geom_point(size = 1) +
    facet_grid(.~wday(Date, label = TRUE)) +
    geom_smooth(se = FALSE)

christmas <- dfman %>%
    filter(Date >= as.Date("2016-12-20") &
               Date <= ("2017-01-03"))

ggplot(christmas, aes(Date, Gross)) +
    geom_label(aes(label = wday(Date, label = TRUE))) +
    geom_line(color = "cornflowerblue") + 
    scale_x_date(date_labels = "%b\n%d",
                 date_breaks = "1 day") +
    ggtitle("Chistmas Week")

ggplot(christmas, aes(Date, Gross/1000000)) +
    geom_line(color = "cornflowerblue", lwd = 1.1) + 
    geom_point(color = "cornflowerblue", size = 2) +
    geom_label(data = christmas, 
               aes(x = Date, y = Gross/1000000 + .06, 
                   label = day(Date))) +
    scale_x_date(date_labels = "%a",
                 date_breaks = "1 day") +
    ggtitle("Manchester by the Sea",
            "Chistmas Week Box Office Gross") +
    labs(x = "Dec 2016 - Jan 2017", 
         y = "Daily Gross (in millions $US)") +
    theme_grey(14)

# annotate Christmas Week
start <- as.Date("2016-12-24")
end <- as.Date("2017-01-02")
g + annotate("rect", xmin = start, xmax = end,
             ymin = -Inf, ymax = Inf, fill = "green",
             alpha = .2) +
    annotate("text", x = end + 2,
             y = 1500000, label = "Dec 24 - Jan 2",
             color = "green", hjust = 0) +
    theme_classic()

# with weekly summary
weekly <- dfman %>%
    group_by(Year = year(Date),
             Week = week(Date)) %>%
    summarize(AvgWeeklyGross = mean(Gross)) %>%
    mutate(Date = as.Date("2015-12-27") +
               365*(Year - 2016) +
               7*(Week -1))

# first attempt
ggplot(dfman, aes(Date, Gross)) +
    geom_line() +
    geom_line(data = weekly,
              aes(Date, AvgWeeklyGross),
              color = "blue") +
    geom_smooth(color = "deeppink")

# cleaned up
ggplot(dfman, aes(Date, Gross/1000000)) +
    geom_line(color = "grey30") +
    geom_line(data = weekly,
              aes(Date, AvgWeeklyGross/1000000),
              color = "blue", lwd = 1.5) +
    geom_smooth(color = "deeppink", lwd = 1.5,
                se = FALSE) +
    annotate("text", x = as.Date("2017-02-15"),
             y = 1.65, label = "average weekly gross",
             color = "blue", hjust = 0) +
    annotate("segment", x = as.Date("2017-02-01"),
             xend = as.Date("2017-02-12"), y = 1.65,
             yend = 1.65, color = "blue", lwd = 1.5) +
    annotate("text", x = as.Date("2017-02-15"),
             y = 1.5, label = "geom_smooth()",
             color = "deeppink", hjust = 0) +
    annotate("segment", x = as.Date("2017-02-01"),
             xend = as.Date("2017-02-12"), y = 1.5,
             yend = 1.5, color = "deeppink", lwd = 1.5) +
    scale_x_date(date_labels = "%b\n%Y") +
    ylab("Daily Box Office Gross \n (in millions US$)") +
    xlab("") +
    ggtitle("Manchester by the Sea",
            "Daily Gross, United States") +
    theme_bw(16)

# weekends
weekends <- dfman %>%
    mutate(daytype = ifelse(wday(Date) %in% c(6, 7, 1),
                            "Fri-Sun", "Mon-Thurs"))
g <- ggplot(weekends, aes(Date, Gross)) +
    geom_line(aes(color = daytype)) +
    theme(legend.title = element_blank())

g